# Research Papers — 2026-03 · bundle page 64 of 243 > Full-text markdown of papers #3151–3200 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/64 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/63.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/65.md) ### Neural Structure Embedding for Symbolic Regression via Continuous Structure Search and Coefficient Optimization Authors: Fateme Memar, Tao Zhe, Dongjie Wang Published: 2026-03-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.22429v1 Symbolic regression aims to discover human-interpretable equations that explain observational data. However, existing approaches rely heavily on discrete structure search (e.g., genetic programming), which often leads to high computational cost, unstable performance, and limited scalability to large equation spaces. To address these challenges, we propose SRCO, a unified embedding-driven framework for symbolic regression that transforms symbolic structures into a continuous, optimizable representation space. The framework consists of three key components: (1) structure embedding: we first generate a large pool of exploratory equations using traditional symbolic regression algorithms and train a Transformer model to compress symbolic structures into a continuous embedding space; (2) continuous structure search: the embedding space enables efficient exploration using gradient-based or sampling-based optimization, significantly reducing the cost of navigating the combinatorial structure space; and (3) coefficient optimization: for each discovered structure, we treat symbolic coefficients as learnable parameters and apply gradient optimization to obtain accurate numerical values. Experiments on synthetic and real-world datasets show that our approach consistently outperforms state-of-the-art methods in equation accuracy, robustness, and search efficiency. This work introduces a new paradigm for symbolic regression by bridging symbolic equation discovery with continuous embedding learning and optimization. --- ### OsteoFlow: Lyapunov-Guided Flow Distillation for Predicting Bone Remodeling after Mandibular Reconstruction Authors: Hamidreza Aftabi, Faye Yu, Brooke Switzer, Zachary Fishman, Eitan Prisman, Antony Hodgson, Cari Whyne, Sidney Fels, Michael Hardisty Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22421v3 Predicting long-term bone remodeling after mandibular reconstruction would be of great clinical benefit, yet standard generative models struggle to maintain trajectory-level consistency and anatomical fidelity over long horizons, particularly in low-data regimes. We introduce OsteoFlow, a flow-based framework predicting Year-1 post-operative CT scans from Day-5 scans. Our core contribution is Lyapunov-guided trajectory distillation: Unlike one-step distillation, our method distills a continuous trajectory over transport time from a registration-derived stationary velocity field teacher. Combined with a resection-aware image loss, this enforces geometric correspondence without sacrificing generative capacity. Evaluated on 344 paired regions of interest, OsteoFlow significantly outperforms state-of-the-art baselines, reducing mean absolute error in the surgical resection zone by ~20%. This highlights the promise of trajectory distillation for long-term prediction in low-data clinical settings. Code is available on GitHub: https://github.com/hamidreza-aftabi/OsteoFlow. --- ### Spatially-Aware Evaluation Framework for Aerial LiDAR Point Cloud Semantic Segmentation: Distance-Based Metrics on Challenging Regions Authors: Alex Salvatierra, José Antonio Sanz, Christian Gutiérrez, Mikel Galar Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22420v1 Semantic segmentation metrics for 3D point clouds, such as mean Intersection over Union (mIoU) and Overall Accuracy (OA), present two key limitations in the context of aerial LiDAR data. First, they treat all misclassifications equally regardless of their spatial context, overlooking cases where the geometric severity of errors directly impacts the quality of derived geospatial products such as Digital Terrain Models. Second, they are often dominated by the large proportion of easily classified points, which can mask meaningful differences between models and under-represent performance in challenging regions. To address these limitations, we propose a novel evaluation framework for comparing semantic segmentation models through two complementary approaches. First, we introduce distance-based metrics that account for the spatial deviation between each misclassified point and the nearest ground-truth point of the predicted class, capturing the geometric severity of errors. Second, we propose a focused evaluation on a common subset of hard points, defined as the points misclassified by at least one of the evaluated models, thereby reducing the bias introduced by easily classified points and better revealing differences in model performance in challenging regions. We validate our framework by comparing three state-of-the-art deep learning models on three aerial LiDAR datasets. Results demonstrate that the proposed metrics provide complementary information to traditional measures, revealing spatial error patterns that are critical for Earth Observation applications but invisible to conventional evaluation approaches. The proposed framework enables more informed model selection for scenarios where spatial consistency is critical. --- ### Computational Arbitrage in AI Model Markets Authors: Ricardo Olmedo, Bernhard Schölkopf, Moritz Hardt Published: 2026-03-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.22404v1 Consider a market of competing model providers selling query access to models with varying costs and capabilities. Customers submit problem instances and are willing to pay up to a budget for a verifiable solution. An arbitrageur efficiently allocates inference budget across providers to undercut the market, thus creating a competitive offering with no model-development risk. In this work, we initiate the study of arbitrage in AI model markets, empirically demonstrating the viability of arbitrage and illustrating its economic consequences. We conduct an in-depth case study of SWE-bench GitHub issue resolution using two representative models, GPT-5 mini and DeepSeek v3.2. In this verifiable domain, simple arbitrage strategies generate net profit margins of up to 40%. Robust arbitrage strategies that generalize across different domains remain profitable. Distillation further creates strong arbitrage opportunities, potentially at the expense of the teacher model's revenue. Multiple competing arbitrageurs drive down consumer prices, reducing the marginal revenue of model providers. At the same time, arbitrage reduces market segmentation and facilitates market entry for smaller model providers by enabling earlier revenue capture. Our results suggest that arbitrage can be a powerful force in AI model markets with implications for model development, distillation, and deployment. --- ### Probabilistic modeling over permutations using quantum computers Authors: Vasilis Belis, Giulio Crognaletti, Matteo Argenton, Michele Grossi, Maria Schuld Published: 2026-03-23 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2603.22401v1 Quantum computers provide a super-exponential speedup for performing a Fourier transform over the symmetric group, an ability for which practical use cases have remained elusive so far. In this work, we leverage this ability to unlock spectral methods for machine learning over permutation-structured data, which appear in applications such as multi-object tracking and recommendation systems. It has been shown previously that a powerful way of building probabilistic models over permutations is to use the framework of non-Abelian harmonic analysis, as the model's group Fourier spectrum captures the interaction complexity: "low frequencies" correspond to low order correlations, and "high frequencies" to more complex ones. This can be used to construct a Markov chain model driven by alternating steps of diffusion (a group-equivariant convolution) and conditioning (a Bayesian update). However, this approach is computationally challenging and hence limited to simple approximations. Here we construct a quantum algorithm that encodes the exact probabilistic model -- a classically intractable object -- into the amplitudes of a quantum state by making use of the Quantum Fourier Transform (QFT) over the symmetric group. We discuss the scaling, limitations, and practical use of such an approach, which we envision to be a first step towards useful applications of non-Abelian QFTs. --- ### Latent Style-based Quantum Wasserstein GAN for Drug Design Authors: Julien Baglio, Yacine Haddad, Richard Polifka Published: 2026-03-23 Categories: quant-ph, cs.AI, cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2603.22399v1 The development of new drugs is a tedious, time-consuming, and expensive process, for which the average costs are estimated to be up to around $2.5 billion. The first step in this long process is the design of the new drug, for which de novo drug design, assisted by artificial intelligence, has blossomed in recent years and revolutionized the field. In particular, generative artificial intelligence has delivered promising results in drug discovery and development, reducing costs and the time to solution. However, classical generative models, such as generative adversarial networks (GANs), are difficult to train due to barren plateaus and prone to mode collapse. Quantum computing may be an avenue to overcome these issues and provide models with fewer parameters, thereby enhancing the generalizability of GANs. We propose a new style-based quantum GAN (QGAN) architecture for drug design that implements noise encoding at every rotational gate of the circuit and a gradient penalty in the loss function to mitigate mode collapse. Our pipeline employs a variational autoencoder to represent the molecular structure in a latent space, which is then used as input to our QGAN. Our baseline model runs on up to 15 qubits to validate our architecture on quantum simulators, and a 156-qubit IBM Heron quantum computer in the five-qubit setup is used for inference to investigate the effects of using real quantum hardware on the analysis. We benchmark our results against classical models as provided by the MOSES benchmark suite. --- ### Efficient Universal Perception Encoder Authors: Chenchen Zhu, Saksham Suri, Cijo Jose, Maxime Oquab, Marc Szafraniec, Wei Wen, Yunyang Xiong, Patrick Labatut, Piotr Bojanowski, Raghuraman Krishnamoorthi, Vikas Chandra Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22387v2 Running AI models on smart edge devices can unlock versatile user experiences, but presents challenges due to limited compute and the need to handle multiple tasks simultaneously. This requires a vision encoder with small size but powerful and versatile representations. We present our method, Efficient Universal Perception Encoder (EUPE), which offers both inference efficiency and universally good representations for diverse downstream tasks. We achieve this by distilling from multiple domain-expert foundation vision encoders. Unlike previous agglomerative methods that directly scale down from multiple teachers to an efficient encoder, we demonstrate the importance of first scaling up to a large proxy teacher and then scaling down from this single teacher. Experiments show that EUPE achieves on-par or better performance than individual domain experts of the same size on diverse task domains and also outperforms previous agglomerative encoders. We release the full family of EUPE models and the code to foster future research. --- ### From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents Authors: Ling Yue, Kushal Raj Bhandari, Ching-Yun Ko, Dhaval Patel, Shuxin Lin, Nianjun Zhou, Jianxi Gao, Pin-Yu Chen, Shaowu Pan Published: 2026-03-23 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.22386v1 Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification. This survey reviews recent methods for designing and optimizing such workflows, which we treat as agentic computation graphs (ACGs). We organize the literature based on when workflow structure is determined, where structure refers to which components or agents are present, how they depend on each other, and how information flows between them. This lens distinguishes static methods, which fix a reusable workflow scaffold before deployment, from dynamic methods, which select, generate, or revise the workflow for a particular run before or during execution. We further organize prior work along three dimensions: when structure is determined, what part of the workflow is optimized, and which evaluation signals guide optimization (e.g., task metrics, verifier signals, preferences, or trace-derived feedback). We also distinguish reusable workflow templates, run-specific realized graphs, and execution traces, separating reusable design choices from the structures actually deployed in a given run and from realized runtime behavior. Finally, we outline a structure-aware evaluation perspective that complements downstream task metrics with graph-level properties, execution cost, robustness, and structural variation across inputs. Our goal is to provide a clear vocabulary, a unified framework for positioning new methods, a more comparable view of existing body of literature, and a more reproducible evaluation standard for future work in workflow optimizations for LLM agents. --- ### Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure Authors: Davide Di Gioia Published: 2026-03-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.22384v2 Autonomous agents operating in continuous environments must decide not only what to do, but when to act. We introduce a lightweight adaptive temporal control system that learns the optimal interval between cognitive ticks from experience, replacing ad hoc biologically inspired timers with a principled learned policy. The policy state is augmented with a predictive hyperbolic spread signal (a "curvature signal" shorthand) derived from hyperbolic geometry: the mean pairwise Poincare distance among n sampled futures embedded in the Poincare ball. High spread indicates a branching, uncertain future and drives the agent to act sooner; low spread signals predictability and permits longer rest intervals. We further propose an interval-aware reward that explicitly penalises inefficiency relative to the chosen wait time, correcting a systematic credit-assignment failure of naive outcome-based rewards in timing problems. We additionally introduce a joint spatio-temporal embedding (ATCPG-ST) that concatenates independently normalised state and position projections in the Poincare ball; spatial trajectory divergence provides an independent timing signal unavailable to the state-only variant (ATCPG-SO). This extension raises mean hyperbolic spread (kappa) from 1.88 to 3.37 and yields a further 5.8 percent efficiency gain over the state-only baseline. Ablation experiments across five random seeds demonstrate that (i) learning is the dominant efficiency factor (54.8 percent over no-learning), (ii) hyperbolic spread provides significant complementary gain (26.2 percent over geometry-free control), (iii) the combined system achieves 22.8 percent efficiency over the fixed-interval baseline, and (iv) adding spatial position information to the spread embedding yields an additional 5.8 percent. --- ### Symbolic Graph Networks for Robust PDE Discovery from Noisy Sparse Data Authors: Xingyu Chen, Junxiu An, Jun Guo, Yuqian Zhou Published: 2026-03-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.22380v1 Data-driven discovery of partial differential equations (PDEs) offers a promising paradigm for uncovering governing physical laws from observational data. However, in practical scenarios, measurements are often contaminated by noise and limited by sparse sampling, which poses significant challenges to existing approaches based on numerical differentiation or integral formulations. In this work, we propose a Symbolic Graph Network (SGN) framework for PDE discovery under noisy and sparse conditions. Instead of relying on local differential approximations, SGN leverages graph message passing to model spatial interactions, providing a non-local representation that is less sensitive to high frequency noise. Based on this representation, the learned latent features are further processed by a symbolic regression module to extract interpretable mathematical expressions. We evaluate the proposed method on several benchmark systems, including the wave equation, convection-diffusion equation, and incompressible Navier-Stokes equations. Experimental results show that SGN can recover meaningful governing relations or solution forms under varying noise levels, and demonstrates improved robustness compared to baseline methods in sparse and noisy settings. These results suggest that combining graph-based representations with symbolic regression provides a viable direction for robust data-driven discovery of physical laws from imperfect observations. The code is available at https://github.com/CXY0112/SGN --- ### Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters Authors: Junyi Zou Published: 2026-03-23 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.22379v1 Adapters are often selected and deployed based on nominal labels (e.g., instruction-tuned), which implicitly suggest what capability improves after adaptation. We test whether nominal training objectives reliably align with realized cross-task capability gains by evaluating the same LoRA adapter across tasks. Our strongest evidence is tied to strict, automatically verifiable instruction following as measured by IFEval: across multiple seeds, base models, and LoRA settings, nominal labels recurrently but not universally fail to predict improvements on this verifiable target, with clear configuration sensitivity including a near-zero or negative case. As an illustrative strongest-case example in a controlled instruction-versus-numeric setting, an instruction-tuned adapter substantially improves off-target NM-based numeric benchmark performance from 0.133 to 0.632 while not improving verifiable instruction following on IFEval (ILA: 0.313 to 0.271; PLA: 0.250 to 0.143; values rounded to three decimals). We refer to this nominal-versus-realized mismatch pattern as capability drift as a descriptive label. The mismatch is visible in the raw cross-task performance matrix; we use a drift score only as a compact summary in the same units as the underlying metrics, not as a new formal metric contribution. Evidence from broader instruction-following benchmarks is benchmark-dependent and mixed, reflecting heterogeneity in how instruction following is operationalized; we therefore do not treat cross-benchmark agreement as a premise. Overall, the practical takeaway is to perform routine cross-task evaluation before deployment and to avoid treating nominal labels as reliable capability proxies. --- ### Abnormalities and Disease Detection in Gastro-Intestinal Tract Images Authors: Zeshan Khan, Muhammad Atif Tahir Published: 2026-03-23 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.22378v1 Gastrointestinal (GI) tract image analysis plays a crucial role in medical diagnosis. This research addresses the challenge of accurately classifying and segmenting GI images for real-time applications, where traditional methods often struggle due to the diversity and complexity of abnormalities. The high computational demands of this domain require efficient and adaptable solutions. This PhD thesis presents a multifaceted approach to GI image analysis. Initially, texture-based feature extraction and classification methods were explored, achieving high processing speed (over 4000 FPS) and strong performance (F1-score: 0.76, Accuracy: 0.98) on the Kvasir V2 dataset. The study then transitions to deep learning, where an optimized model combined with data bagging techniques improved performance, reaching an accuracy of 0.92 and an F1-score of 0.60 on the HyperKvasir dataset, and an F1-score of 0.88 on Kvasir V2. To support real-time detection, a streamlined neural network integrating texture and local binary patterns was developed. By addressing inter-class similarity and intra-class variation through a learned threshold, the system achieved 41 FPS with high accuracy (0.99) and an F1-score of 0.91 on HyperKvasir. Additionally, two segmentation tools are proposed to enhance usability, leveraging Depth-Wise Separable Convolution and neural network ensembles for improved detection, particularly in low-FPS scenarios. Overall, this research introduces novel and adaptable methodologies, progressing from traditional texture-based techniques to deep learning and ensemble approaches, providing a comprehensive framework for advancing GI image analysis. --- ### Closing the Auto-Research Loop: An AI Co-Scientist for Production Search Ranking Authors: Liwei Wu, Cho-Jui Hsieh Published: 2026-03-23 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.22376v2 We present an AI Co-Scientist framework that closes the research loop for the production search-ranking system of a large online travel platform -- pairing LLM agents with direct cloud-compute access so that idea generation, code implementation, GPU experimentation, and result analysis iterate end-to-end with a human scientist in the loop. The framework uses a hybrid agent architecture: single-LLM agents handle routine work, while multi-LLM consensus (GPT-5.2, Gemini Pro 3, Claude Opus 4.5) is invoked for higher-stakes decisions. On the production ranking task, a human-designed transformer baseline (V2) yielded $+0.118\%$ over a pre-transformer baseline (V1); the AI Co-Scientist's automated loop on top of V2 contributed an additional $+0.083\%$, for a combined $+0.201\%$ offline gain delivered in roughly one extra week of wall-clock time (single-run numbers; statistical limits discussed in the paper). The most useful AI proposals -- unified long-sequence layouts, slot-type embeddings, and multi-phase learning-rate schedules -- are standard practice in NLP and Vision but were absent from our production stack, suggesting that LLM agents can serve as cross-disciplinary connectors for ranking teams. We also report deployment context, negative results, and lessons learned. --- ### Three Creates All: You Only Sample 3 Steps Authors: Yuren Cai, Guangyi Wang, Zongqing Li, Li Li, Zhihui Liu, Songzhi Su Published: 2026-03-23 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.22375v1 Diffusion models deliver high-fidelity generation but remain slow at inference time due to many sequential network evaluations. We find that standard timestep conditioning becomes a key bottleneck for few-step sampling. Motivated by layer-dependent denoising dynamics, we propose Multi-layer Time Embedding Optimization (MTEO), which freeze the pretrained diffusion backbone and distill a small set of step-wise, layer-wise time embeddings from reference trajectories. MTEO is plug-and-play with existing ODE solvers, adds no inference-time overhead, and trains only a tiny fraction of parameters. Extensive experiments across diverse datasets and backbones show state-of-the-art performance in the few-step sampling and substantially narrow the gap between distillation-based and lightweight methods. Code will be available. --- ### Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion Authors: Seunghan Lee, Jun Seo, Jaehoon Lee, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, SoonYoung Lee, Wonbin Ahn Published: 2026-03-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.22372v3 Recent advances in multimodal learning have motivated the integration of auxiliary modalities such as text or vision into time series (TS) forecasting. However, most existing methods provide limited gains, often improving performance only in specific datasets or relying on architecture-specific designs that limit generalization. In this paper, we show that multimodal models with naive fusion strategies (e.g., simple addition or concatenation) often underperform unimodal TS models, which we attribute to the uncontrolled integration of auxiliary modalities which may introduce irrelevant information. Motivated by this observation, we explore various constrained fusion methods designed to control such integration and find that they consistently outperform naive fusion methods. Furthermore, we propose Controlled Fusion Adapter (CFA), a simple plug-in method that enables controlled cross-modal interactions without modifying the TS backbone, integrating only relevant textual information aligned with TS dynamics. CFA employs low rank adapters to filter irrelevant textual information before fusing it into temporal representations. We conduct over 20K experiments across various datasets and TS/text models, demonstrating the effectiveness of the constrained fusion methods. Code is available at: https://github.com/seunghan96/cfa. --- ### FAAR: Format-Aware Adaptive Rounding for NVFP4 Authors: Hanglin Li, Shuchang Tian, Chen Lin, Zhiyong Zhao, Kun Zhan Published: 2026-03-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.22370v1 Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such as NVFP4 offer a promising solution for reducing memory footprint and accelerating computation. However, existing quantization methods typically rely on conventional rounding strategies and fail to account for the non-uniformity of the NVFP4 numerical grid, resulting in suboptimal rounding decisions and amplified quantization errors. To address this, we propose Format-Aware Adaptive Rounding (FAAR), a learnable rounding strategy tailored for the NVFP4 format. Unlike conventional quantization paradigms, FAAR explicitly incorporates the non-uniform NVFP4 grid into the optimization process. By adaptively adjusting rounding decisions guided by loss gradients, our method effectively approximates the theoretically optimal quantization. To complement FAAR, we introduce a 2-stages Format Alignment (2FA) fine-tuning scheme that aligns LLM parameters layer-by-layer to the NVFP4 numerical space, further narrowing the performance gap. Remarkably, this learnable optimization incurs a minimal training overhead of only 4 GPU hours on Llama3-1B. Extensive experiments demonstrate the effectiveness of our approach. Compared with Round-to-Nearest (RTN), our method reduces perplexity on WikiText-2 from 14.28 to 12.60 on Llama3-1B and from 23.06 to 21.27 on Qwen3-1.7B. Additionally, our method consistently outperforms state-of-the-art approaches across various zero-shot downstream tasks. --- ### SynLeaF: A Dual-Stage Multimodal Fusion Framework for Synthetic Lethality Prediction Across Pan- and Single-Cancer Contexts Authors: Zheming Xing, Siyuan Zhou, Ruinan Wang, Rui Han, Shiming Zhang, Shiqu Chen, Yurui Huang, Jiahao Ma, Yifan Chen, Xuan Wang, Yadong Wang, Junyi Li Published: 2026-03-23 Categories: q-bio.GN, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.22369v1 Accurate prediction of synthetic lethality (SL) is important for guiding the development of cancer drugs and therapies. SL prediction faces significant challenges in the effective fusion of heterogeneous multi-source data. Existing multimodal methods often suffer from "modality laziness" due to disparate convergence speeds, which hinders the exploitation of complementary information. This is also one reason why most existing SL prediction models cannot perform well on both pan-cancer and single-cancer SL pair prediction. In this study, we propose SynLeaF, a dual-stage multimodal fusion framework for SL prediction across pan- and single-cancer contexts. The framework employs a VAE-based cross-encoder with a product of experts mechanism to fuse four omics data types (gene expression, mutation, methylation, and CNV), while simultaneously utilizing a relational graph convolutional network to capture structured gene representations from biomedical knowledge graphs. To mitigate modality laziness, SynLeaF introduces a dual-stage training mechanism employing featurelevel knowledge distillation with adaptive uni-modal teacher and ensemble strategies. In extensive experiments across eight specific cancer types and a pancancer dataset, SynLeaF achieves superior performance in 17 out of 19 scenarios. Ablation studies and gradient analyses further validate the critical contributions of the proposed fusion and distillation mechanisms to model robustness and generalization. To facilitate community use, a web server is available at https://synleaf.bioinformatics-lilab.cn. --- ### When Visuals Aren't the Problem: Evaluating Vision-Language Models on Misleading Data Visualizations Authors: Harsh Nishant Lalai, Raj Sanjay Shah, Hanspeter Pfister, Sashank Varma, Grace Guo Published: 2026-03-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.22368v2 Visualizations help communicate data insights, but deceptive data representations can distort their interpretation and propagate misinformation. While recent Vision Language Models (VLMs) perform well on many chart understanding tasks, their ability to detect misleading visualizations, especially when deception arises from subtle reasoning errors in captions, remains poorly understood. Here, we evaluate VLMs on misleading visualization-caption pairs grounded in a fine-grained taxonomy of reasoning errors (e.g., Cherry-picking, Causal inference) and visualization design errors (e.g., Truncated axis, Dual axis, inappropriate encodings). To this end, we develop a benchmark that combines real-world visualization with human-authored, curated misleading captions designed to elicit specific reasoning and visualization error types, enabling controlled analysis across error categories and modalities of misleadingness. Evaluating many commercial and open-source VLMs, we find that models detect visual design errors substantially more reliably than reasoning-based misinformation, and frequently misclassify non-misleading visualizations as deceptive. Overall, our work fills a gap between coarse detection of misleading content and the attribution of the specific reasoning or visualization errors that give rise to it. --- ### Reasoner-Executor-Synthesizer: Scalable Agentic Architecture with Static O(1) Context Window Authors: Ivan Dobrovolskyi Published: 2026-03-23 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.22367v1 Large Language Models (LLMs) deployed as autonomous agents commonly use Retrieval-Augmented Generation (RAG), feeding retrieved documents into the context window, which creates two problems: the risk of hallucination grows with context length, and token cost scales linearly with dataset size. We propose the Reasoner-Executor-Synthesizer (RES) architecture, a three-layer design that strictly separates intent parsing (Reasoner), deterministic data retrieval and aggregation (Executor), and narrative generation (Synthesizer). The Executor uses zero LLM tokens and passes only fixed-size statistical summaries to the Synthesizer. We formally prove that RES achieves O(1) token complexity with respect to dataset size, and validate this on ScholarSearch, a scholarly research assistant backed by the Crossref API (130M+ articles). Across 100 benchmark runs, RES achieves a mean token cost of 1,574 tokens regardless of whether the dataset contains 42,000 or 16.3 million articles. The architecture eliminates data hallucination by construction: the LLM never sees raw records. KEYWORDS LLM agents; agentic architecture; hallucination elimination; token optimization; context window; retrieval-augmented generation; deterministic execution; scholarly metadata; Crossref API; O(1) complexity. --- ### Modeling Quantum Federated Autoencoder for Anomaly Detection in IoT Networks Authors: Devashish Chaudhary, Sutharshan Rajasegarar, Shiva Raj Pokhrel Published: 2026-03-23 Categories: quant-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.22366v1 We propose a Quantum Federated Autoencoder for Anomaly Detection, a framework that leverages quantum federated learning for efficient, secure, and distributed processing in IoT networks. By harnessing quantum autoencoders for high-dimensional feature representation and federated learning for decentralized model training, the approach transforms localized learning on edge devices without requiring transmission of raw data, thereby preserving privacy and minimizing communication overhead. The model leverages quantum advantage in pattern recognition to enhance detection sensitivity, particularly in complex and dynamic IoT network traffic. Experiments on a real-world IoT dataset show that the proposed method delivers anomaly detection accuracy and robustness comparable to centralized approaches, while ensuring data privacy. --- ### Q-AGNN: Quantum-Enhanced Attentive Graph Neural Network for Intrusion Detection Authors: Devashish Chaudhary, Sutharshan Rajasegarar, Shiva Raj Pokhrel Published: 2026-03-23 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.22365v1 With the rapid growth of interconnected devices, accurately detecting malicious activities in network traffic has become increasingly challenging. Most existing deep learning-based intrusion detection systems treat network flows as independent instances, thereby failing to exploit the relational dependencies inherent in network communications. To address this limitation, we propose Q-AGNN, a Quantum-Enhanced Attentive Graph Neural Network for intrusion detection, where network flows are modeled as nodes and edges represent similarity relationships. Q-AGNN leverages parameterized quantum circuits (PQCs) to encode multi-hop neighborhood information into a high-dimensional latent space, inducing a bounded quantum feature map that implements a second-order polynomial graph filter in a quantum-induced Hilbert space. An attention mechanism is subsequently applied to adaptively weight the quantum-enhanced embeddings, allowing the model to focus on the most influential nodes contributing to anomalous behavior. Extensive experiments conducted on four benchmark intrusion detection datasets demonstrate that Q-AGNN achieves competitive or superior detection performance compared to state-of-the-art graph-based methods, while consistently maintaining low false positive rates under hardware-calibrated noise conditions. Moreover, we also executed the Q-AGNN framework on actual IBM quantum hardware to demonstrate the practical operability of the proposed pipeline under real NISQ conditions. These results highlight the effectiveness of integrating quantum-enhanced representations with attention mechanisms for graph-based intrusion detection and underscore the potential of hybrid quantum-classical learning frameworks in cybersecurity applications. --- ### MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives Authors: Xiang Li, Yixuan Jia, Xiao Li, Jeffrey A. Fessler, Rongrong Wang, Qing Qu Published: 2026-03-23 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.22364v3 Diffusion models achieve strong performance in generative modeling, but their success often relies heavily on classifier-free guidance (CFG), an inference-time heuristic that modifies the sampling trajectory. In theory, diffusion models trained with standard denoising score matching (DSM) should recover the target data distribution, raising two fundamental questions: (i) why is inference-time guidance necessary in practice, and (ii) can its underlying effect be internalized into a principled training objective? In this work, we argue that a key limitation of standard DSM is insufficient inter-class separation. To address this issue, we propose MCLR, an alignment objective that explicitly maximizes inter-class likelihood-ratios during training. Fine-tuning diffusion models with MCLR induces CFG-like improvements under standard sampling, substantially improving guidance-free conditional generation and narrowing the gap to inference-time CFG. Beyond these empirical benefits, we show theoretically that the CFG-guided score is exactly the optimal solution to a sample-adaptive weighted MCLR objective. This result connects CFG to alignment-based objectives, providing a mechanistic interpretation of CFG as an implicit inference-time contrastive alignment procedure. --- ### Early Discoveries of Algorithmist I: Promise of Provable Algorithm Synthesis at Scale Authors: Janardhan Kulkarni Published: 2026-03-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.22363v1 Designing algorithms with provable guarantees that also work well in practice remains difficult, requiring both mathematical reasoning and careful implementation. Existing approaches that bridge worst-case theory and empirical performance, such as beyond-worst-case analysis and data-driven algorithm selection, typically assume prior distributional knowledge or restrict attention to a fixed pool of algorithms. Recent progress in LLMs suggests a new possibility: provable algorithm synthesis on the fly. To study this, we built Algorithmist, an autonomous researcher agent on top of GitHub Copilot that runs a multi-agent research-and-review loop, with separate stages for idea generation, algorithm and proof development, proof-guided implementation, and review of proofs, code, and their alignment. We evaluate Algorithmist on research-level tasks in private data analysis and clustering. When asked to design practical methods that jointly satisfy privacy, approximation, and interpretability requirements, it produced provably sound and empirically effective algorithms, together with research-style writeups and audited implementations. It also found improved algorithms in some settings, explained principled barriers in others, and uncovered a subtle proof bug in prior published work. More broadly, our results suggest a new paradigm in which LLM systems generate research-paper-quality algorithmic artifacts tailored to each dataset and deployment setting. They also point to a proof-first code-synthesis paradigm, in which code is developed alongside a structured natural-language proof intermediate representation and kept aligned with it throughout synthesis. --- ### Unveiling the Mechanism of Continuous Representation Full-Waveform Inversion: A Wave Based Neural Tangent Kernel Framework Authors: Ruihua Chen, Yisi Luo, Bangyu Wu, Deyu Meng Published: 2026-03-23 Categories: cs.LG, cs.AI, physics.geo-ph arXiv: https://arxiv.org/abs/2603.22362v1 Full-waveform inversion (FWI) estimates physical parameters in the wave equation from limited measurements and has been widely applied in geophysical exploration, medical imaging, and non-destructive testing. Conventional FWI methods are limited by their notorious sensitivity to the accuracy of the initial models. Recent progress in continuous representation FWI (CR-FWI) demonstrates that representing parameter models with a coordinate-based neural network, such as implicit neural representation (INR), can mitigate the dependence on initial models. However, its underlying mechanism remains unclear, and INR-based FWI shows slower high-frequency convergence. In this work, we investigate the general CR-FWI framework and develop a unified theoretical understanding by extending the neural tangent kernel (NTK) for FWI to establish a wave-based NTK framework. Unlike standard NTK, our analysis reveals that wave-based NTK is not constant, both at initialization and during training, due to the inherent nonlinearity of FWI. We further show that the eigenvalue decay behavior of the wave-based NTK can explain why CR-FWI alleviates the dependency on initial models and shows slower high-frequency convergence. Building on these insights, we propose several CR-FWI methods with tailored eigenvalue decay properties for FWI, including a novel hybrid representation combining INR and multi-resolution grid (termed IG-FWI) that achieves a more balanced trade-off between robustness and high-frequency convergence rate. Applications in geophysical exploration on Marmousi, 2D SEG/EAGE Salt and Overthrust, 2004 BP model, and the more realistic 2014 Chevron models show the superior performance of our proposed methods compared to conventional FWI and existing INR-based FWI methods. --- ### WorldCache: Content-Aware Caching for Accelerated Video World Models Authors: Umair Nawaz, Ahmed Heakl, Ufaq Khan, Abdelrahman Shaker, Salman Khan, Fahad Shahbaz Khan Published: 2026-03-23 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.22286v1 Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing intermediate activations across denoising steps; however, existing methods largely rely on a Zero-Order Hold assumption i.e., reusing cached features as static snapshots when global drift is small. This often leads to ghosting artifacts, blur, and motion inconsistencies in dynamic scenes. We propose \textbf{WorldCache}, a Perception-Constrained Dynamical Caching framework that improves both when and how to reuse features. WorldCache introduces motion-adaptive thresholds, saliency-weighted drift estimation, optimal approximation via blending and warping, and phase-aware threshold scheduling across diffusion steps. Our cohesive approach enables adaptive, motion-consistent feature reuse without retraining. On Cosmos-Predict2.5-2B evaluated on PAI-Bench, WorldCache achieves \textbf{2.3$\times$} inference speedup while preserving \textbf{99.4\%} of baseline quality, substantially outperforming prior training-free caching approaches. Our code can be accessed on \href{https://umair1221.github.io/World-Cache/}{World-Cache}. --- ### VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding Authors: Ruoliu Yang, Chu Wu, Caifeng Shan, Ran He, Chaoyou Fu Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22285v2 Long video understanding remains challenging for multimodal large language models (MLLMs) due to limited context windows, which necessitate identifying sparse query-relevant video segments. However, existing methods predominantly localize clues based solely on the query, overlooking the video's intrinsic structure and varying relevance across segments. To address this, we propose VideoDetective, a framework that integrates query-to-segment relevance and inter-segment affinity for effective clue hunting in long-video question answering. Specifically, we divide a video into various segments and represent them as a visual-temporal affinity graph built from visual similarity and temporal proximity. We then perform a Hypothesis-Verification-Refinement loop to estimate relevance scores of observed segments to the query and propagate them to unseen segments, yielding a global relevance distribution that guides the localization of the most critical segments for final answering with sparse observation. Experiments show our method consistently achieves substantial gains across a wide range of mainstream MLLMs on representative benchmarks, with accuracy improvements of up to 7.5% on VideoMME-long. Our code is available at https://videodetective.github.io/ --- ### End-to-End Training for Unified Tokenization and Latent Denoising Authors: Shivam Duggal, Xingjian Bai, Zongze Wu, Richard Zhang, Eli Shechtman, Antonio Torralba, Phillip Isola, William T. Freeman Published: 2026-03-23 Categories: cs.CV, cs.AI, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2603.22283v1 Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be trained in the frozen latent space. We propose UNITE - an autoencoder architecture for unified tokenization and latent diffusion. UNITE consists of a Generative Encoder that serves as both image tokenizer and latent generator via weight sharing. Our key insight is that tokenization and generation can be viewed as the same latent inference problem under different conditioning regimes: tokenization infers latents from fully observed images, whereas generation infers them from noise together with text or class conditioning. Motivated by this, we introduce a single-stage training procedure that jointly optimizes both tasks via two forward passes through the same Generative Encoder. The shared parameters enable gradients to jointly shape the latent space, encouraging a "common latent language". Across image and molecule modalities, UNITE achieves near state of the art performance without adversarial losses or pretrained encoders (e.g., DINO), reaching FID 2.12 and 1.73 for Base and Large models on ImageNet 256 x 256. We further analyze the Generative Encoder through the lenses of representation alignment and compression. These results show that single stage joint training of tokenization & generation from scratch is feasible. --- ### UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation Authors: Ziyi Wang, Xinshun Wang, Shuang Chen, Yang Cong, Mengyuan Liu Published: 2026-03-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.22282v2 We present UniMotion, to our knowledge the first unified framework for simultaneous understanding and generation of human motion, natural language, and RGB images within a single architecture. Existing unified models handle only restricted modality subsets (e.g., Motion-Text or static Pose-Image) and predominantly rely on discrete tokenization, which introduces quantization errors and disrupts temporal continuity. UniMotion overcomes both limitations through a core principle: treating motion as a first-class continuous modality on equal footing with RGB. A novel Cross-Modal Aligned Motion VAE (CMA-VAE) and symmetric dual-path embedders construct parallel continuous pathways for Motion and RGB within a shared LLM backbone. To inject visual-semantic priors into motion representations without requiring images at inference, we propose Dual-Posterior KL Alignment (DPA), which distills a vision-fused encoder's richer posterior into the motion-only encoder. To address the cold-start problem -- where text supervision alone is too sparse to calibrate the newly introduced motion pathway -- we further propose Latent Reconstruction Alignment (LRA), a self-supervised pre-training strategy that uses dense motion latents as unambiguous conditions to co-calibrate the embedder, backbone, and flow head, establishing a stable motion-aware foundation for all downstream tasks. UniMotion achieves state-of-the-art performance across seven tasks spanning any-to-any understanding, generation, and editing among the three modalities, with especially strong advantages on cross-modal compositional tasks. --- ### ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model Authors: Haichao Zhang, Yijiang Li, Shwai He, Tushar Nagarajan, Mingfei Chen, Jianglin Lu, Ang Li, Yun Fu Published: 2026-03-23 Categories: cs.CV, cs.AI, cs.CL, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.22281v2 Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can bias predictors toward local, low-level extrapolation, making it difficult to capture long-horizon semantics and reducing downstream utility. Vision--language models (VLMs), in contrast, provide strong semantic grounding and general knowledge by reasoning over uniformly sampled frames, but they are not ideal as standalone dense predictors due to compute-driven sparse sampling, a language-output bottleneck that compresses fine-grained interaction states into text-oriented representations, and a data-regime mismatch when adapting to small action-conditioned datasets. We propose a VLM-guided JEPA-style latent world modeling framework that combines dense-frame dynamics modeling with long-horizon semantic guidance via a dual-temporal pathway: a dense JEPA branch for fine-grained motion and interaction cues, and a uniformly sampled VLM \emph{thinker} branch with a larger temporal stride for knowledge-rich guidance. To transfer the VLM's progressive reasoning signals effectively, we introduce a hierarchical pyramid representation extraction module that aggregates multi-layer VLM representations into guidance features compatible with latent prediction. Experiments on hand-manipulation trajectory prediction show that our method outperforms both a strong VLM-only baseline and a JEPA-predictor baseline, and yields more robust long-horizon rollout behavior. --- ### DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models Authors: Zhide Zhong, Junfeng Li, Junjie He, Haodong Yan, Xin Gong, Guanyi Zhao, Yingjie Cai, Jiantao Gao, Xu Yan, Bingbing Liu, Yingcong Chen, Liuqing Yang et al. Published: 2026-03-23 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.22280v1 Vision-Language-Action (VLA) models map visual observations and language instructions directly to robotic actions. While effective for simple tasks, standard VLA models often struggle with complex, multi-step tasks requiring logical planning, as well as precise manipulations demanding fine-grained spatial perception. Recent efforts have incorporated Chain-of-Thought (CoT) reasoning to endow VLA models with a ``thinking before acting'' capability. However, current CoT-based VLA models face two critical limitations: 1) an inability to simultaneously capture low-level visual details and high-level logical planning due to their reliance on isolated, single-modal CoT; 2) high inference latency with compounding errors caused by step-by-step autoregressive decoding. To address these limitations, we propose DualCoT-VLA, a visual-linguistic CoT method for VLA models with a parallel reasoning mechanism. To achieve comprehensive multi-modal reasoning, our method integrates a visual CoT for low-level spatial understanding and a linguistic CoT for high-level task planning. Furthermore, to overcome the latency bottleneck, we introduce a parallel CoT mechanism that incorporates two sets of learnable query tokens, shifting autoregressive reasoning to single-step forward reasoning. Extensive experiments demonstrate that our DualCoT-VLA achieves state-of-the-art performance on the LIBERO and RoboCasa GR1 benchmarks, as well as in real-world platforms. --- ### 3D-Layout-R1: Structured Reasoning for Language-Instructed Spatial Editing Authors: Haoyu Zhen, Xiaolong Li, Yilin Zhao, Han Zhang, Sifei Liu, Kaichun Mo, Chuang Gan, Subhashree Radhakrishnan Published: 2026-03-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.22279v1 Large Language Models (LLMs) and Vision Language Models (VLMs) have shown impressive reasoning abilities, yet they struggle with spatial understanding and layout consistency when performing fine-grained visual editing. We introduce a Structured Reasoning framework that performs text-conditioned spatial layout editing via scene-graph reasoning. Given an input scene graph and a natural-language instruction, the model reasons over the graph to generate an updated scene graph that satisfies the text condition while maintaining spatial coherence. By explicitly guiding the reasoning process through structured relational representations, our approach improves both interpretability and control over spatial relationships. We evaluate our method on a new text-guided layout editing benchmark encompassing sorting, spatial alignment, and room-editing tasks. Our training paradigm yields an average 15% improvement in IoU and 25% reduction in center-distance error compared to Chain of Thought Fine-tuning (CoT-SFT) and vanilla GRPO baselines. Compared to SOTA zero-shot LLMs, our best models achieve up to 20% higher mIoU, demonstrating markedly improved spatial precision. --- ### The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models Authors: Kelly Cui, Nikhil Prakash, Shoval Messica, Ayush Raina, David Bau, Antonio Torralba, Tamar Rott Shaham Published: 2026-03-23 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.22278v2 Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to bind objects with their properties and spatial relations. Yet it remains unclear where and how such associations are computed within VLMs. In this work, we show that VLMs rely on two concurrent mechanisms to represent spatial variable binding. In the language model backbone, intermediate layers represent content-independent spatial relations on top of visual tokens corresponding to objects. However, this mechanism plays only a secondary role in shaping model predictions. Instead, the dominant source of spatial information originates in the vision encoder, whose representations encode the layout of objects and are directly exploited by the language model backbone. Notably, this spatial signal is distributed globally across visual tokens, extending beyond object regions into surrounding background areas. We show that enhancing these vision-derived spatial representations globally across all image tokens improves spatial variable binding performance across models of various sizes on complex natural images from the COCO datasets. Together, our results clarify how spatial variable binding is computed within VLMs and highlight the central role of vision encoders in enabling it. --- ### Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels Authors: Alexandra Zelenin, Alexandra Zhuravlyova Published: 2026-03-23 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.22276v1 Weight-Decomposed Low-Rank Adaptation (DoRA) extends LoRA by decoupling weight magnitude from direction, but its forward pass requires the row-wise norm of W + sBA, a computation that every major framework we surveyed implements by materializing the dense (d_out, d_in) product BA. At d_in = 8192 and rank r = 384, a single module's norm requires about 512 MB of transient working memory in bf16, making high-rank DoRA costly and often infeasible on common single-GPU setups once hundreds of adapted modules and checkpointing are involved. We present two systems contributions. A factored norm decomposes the squared norm into base, cross, and Gram terms computable through O(d_out r + r^2) intermediates, eliminating the dense product. Fused Triton kernels collapse the four-kernel DoRA composition into a single pass, reducing memory traffic by about 4x and using a numerically stable form that avoids catastrophic cancellation in the near-unity rescaling regime where magnitude scales concentrate in practice. Across six 8-32B vision-language models (VLMs) on three NVIDIA GPUs (RTX 6000 PRO, H200, B200) at r = 384 in bf16, the fused implementation is 1.5-2.0x faster than Hugging Face PEFT's DoRA implementation for inference and 1.5-1.9x faster for gradient computation (optimizer step excluded), with up to 7 GB lower peak VRAM. Microbenchmarks on six GPUs spanning four architecture generations (L40S, A100, RTX 6000 PRO, H200, B200, B300) confirm 1.5-2.7x compose-kernel speedup. Final-logit cosine similarity exceeds 0.9999 across all model/GPU pairs, and multi-seed training curves match within 7.1 x 10^-4 mean per-step loss delta over 2000 steps. --- ### Repurposing Geometric Foundation Models for Multi-view Diffusion Authors: Wooseok Jang, Seonghu Jeon, Jisang Han, Jinhyeok Choi, Minkyung Kwon, Seungryong Kim, Saining Xie, Sainan Liu Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22275v1 While recent advances in generative latent spaces have driven substantial progress in single-image generation, the optimal latent space for novel view synthesis (NVS) remains largely unexplored. In particular, NVS requires geometrically consistent generation across viewpoints, but existing approaches typically operate in a view-independent VAE latent space. In this paper, we propose Geometric Latent Diffusion (GLD), a framework that repurposes the geometrically consistent feature space of geometric foundation models as the latent space for multi-view diffusion. We show that these features not only support high-fidelity RGB reconstruction but also encode strong cross-view geometric correspondences, providing a well-suited latent space for NVS. Our experiments demonstrate that GLD outperforms both VAE and RAE on 2D image quality and 3D consistency metrics, while accelerating training by more than 4.4x compared to the VAE latent space. Notably, GLD remains competitive with state-of-the-art methods that leverage large-scale text-to-image pretraining, despite training its diffusion model from scratch without such generative pretraining. --- ### Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration Authors: Zakaria Mhammedi, James Cohan Published: 2026-03-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.22273v4 The process of discovery requires active exploration -- the act of collecting new and informative data. However, efficient autonomous exploration remains a major unsolved problem. The dominant paradigm addresses this challenge by using Reinforcement Learning (RL) to train agents with intrinsic motivation, maximizing a composite objective of extrinsic and intrinsic rewards. We suggest that this approach incurs unnecessary overhead: while policy optimization is necessary for precise task execution, employing such machinery solely to expand state coverage may be inefficient. In this paper, we propose a new approach that explicitly decouples exploration from policy optimization and bypasses RL entirely during the exploration phase. Our method uses a tree-search strategy inspired by the Go-With-The-Winner algorithm, paired with a measure of uncertainty to systematically drive exploration. By removing the overhead of policy optimization, our approach explores an order of magnitude more efficiently than standard intrinsic motivation baselines on hard exploration benchmarks. Further, we demonstrate that the trajectories discovered during exploration can be distilled into deployable policies using existing supervised backward learning algorithms, achieving state-of-the-art performance by a wide margin on Montezuma's Revenge, Pitfall!, and Venture without relying on domain-specific knowledge. Finally, we demonstrate the generality of our framework in high-dimensional continuous action spaces by solving the MuJoCo Adroit dexterous manipulation and AntMaze tasks in a sparse-reward setting, directly from image observations and without expert demonstrations or offline datasets. To the best of our knowledge, this has not been achieved before for the Adroit tasks. --- ### DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution Authors: Zhengyao Lv, Menghan Xia, Xintao Wang, Kwan-Yee K. Wong Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22271v1 Diffusion-based video super-resolution (VSR) has recently achieved remarkable fidelity but still suffers from prohibitive sampling costs. While distribution matching distillation (DMD) can accelerate diffusion models toward one-step generation, directly applying it to VSR often results in training instability alongside degraded and insufficient supervision. To address these issues, we propose DUO-VSR, a three-stage framework built upon a Dual-Stream Distillation strategy that unifies distribution matching and adversarial supervision for one-step VSR. Firstly, a Progressive Guided Distillation Initialization is employed to stabilize subsequent training through trajectory-preserving distillation. Next, the Dual-Stream Distillation jointly optimizes the DMD and Real-Fake Score Feature GAN (RFS-GAN) streams, with the latter providing complementary adversarial supervision leveraging discriminative features from both real and fake score models. Finally, a Preference-Guided Refinement stage further aligns the student with perceptual quality preferences. Extensive experiments demonstrate that DUO-VSR achieves superior visual quality and efficiency over previous one-step VSR approaches. --- ### GenOpticalFlow: A Generative Approach to Unsupervised Optical Flow Learning Authors: Yixuan Luo, Feng Qiao, Zhexiao Xiong, Yanjing Li, Nathan Jacobs Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22270v1 Optical flow estimation is a fundamental problem in computer vision, yet the reliance on expensive ground-truth annotations limits the scalability of supervised approaches. Although unsupervised and semi-supervised methods alleviate this issue, they often suffer from unreliable supervision signals based on brightness constancy and smoothness assumptions, leading to inaccurate motion estimation in complex real-world scenarios. To overcome these limitations, we introduce \textbf{\modelname}, a novel framework that synthesizes large-scale, perfectly aligned frame--flow data pairs for supervised optical flow training without human annotations. Specifically, our method leverages a pre-trained depth estimation network to generate pseudo optical flows, which serve as conditioning inputs for a next-frame generation model trained to produce high-fidelity, pixel-aligned subsequent frames. This process enables the creation of abundant, high-quality synthetic data with precise motion correspondence. Furthermore, we propose an \textit{inconsistent pixel filtering} strategy that identifies and removes unreliable pixels in generated frames, effectively enhancing fine-tuning performance on real-world datasets. Extensive experiments on KITTI2012, KITTI2015, and Sintel demonstrate that \textbf{\modelname} achieves competitive or superior results compared to existing unsupervised and semi-supervised approaches, highlighting its potential as a scalable and annotation-free solution for optical flow learning. We will release our code upon acceptance. --- ### TiCo: Time-Controllable Spoken Dialogue Model Authors: Kai-Wei Chang, Wei-Chih Chen, En-Pei Hu, Hung-yi Lee, James Glass Published: 2026-03-23 Categories: cs.CL, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2603.22267v2 We introduce TiCo, a time-controllable spoken dialogue model (SDM) that follows time-constrained instructions (e.g., "Please generate a response lasting about 15 seconds") and generates spoken responses with controllable duration. This capability is valuable for real-world spoken language systems such as voice assistants and interactive agents, where controlling response duration can improve interaction quality. However, despite their strong ability to generate natural spoken responses, existing models lack time awareness and struggle to follow duration-related instructions. To systematically evaluate this, we introduce TiCo-Bench, the first benchmark for time-controllable instruction following in SDMs, on which existing open-source and commercial models frequently fail to satisfy explicit time constraints. TiCo addresses this limitation by enabling an SDM to estimate elapsed speaking time during generation through Spoken Time Markers (STM) (e.g., <10.6 seconds>). These markers help the model maintain awareness of time and adjust the remaining content to meet the target duration. TiCo is post-trained efficiently without question-answer paired data, relying on self-generation and reinforcement learning with verifiable reward. Experimental results show that TiCo reduces duration error by 2.7x over its backbone and 1.6x over the strongest baseline, while preserving response quality. --- ### Greater accessibility can amplify discrimination in generative AI Authors: Carolin Holtermann, Minh Duc Bui, Kaitlyn Zhou, Valentin Hofmann, Katharina von der Wense, Anne Lauscher Published: 2026-03-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.22260v1 Hundreds of millions of people rely on large language models (LLMs) for education, work, and even healthcare. Yet these models are known to reproduce and amplify social biases present in their training data. Moreover, text-based interfaces remain a barrier for many, for example, users with limited literacy, motor impairments, or mobile-only devices. Voice interaction promises to expand accessibility, but unlike text, speech carries identity cues that users cannot easily mask, raising concerns about whether accessibility gains may come at the cost of equitable treatment. Here we show that audio-enabled LLMs exhibit systematic gender discrimination, shifting responses toward gender-stereotyped adjectives and occupations solely on the basis of speaker voice, and amplifying bias beyond that observed in text-based interaction. Thus, voice interfaces do not merely extend text models to a new modality but introduce distinct bias mechanisms tied to paralinguistic cues. Complementary survey evidence ($n=1,000$) shows that infrequent chatbot users are most hesitant to undisclosed attribute inference and most likely to disengage when such practices are revealed. To demonstrate a potential mitigation strategy, we show that pitch manipulation can systematically regulate gender-discriminatory outputs. Overall, our findings reveal a critical tension in AI development: efforts to expand accessibility through voice interfaces simultaneously create new pathways for discrimination, demanding that fairness and accessibility be addressed in tandem. --- ### Characterizing High-Capacity Janus Aminobenzene-Graphene Anode for Sodium-Ion Batteries with Machine Learning Authors: Claudia Islas-Vargas, L. Ricardo Montoya, Carlos A. Vital-José, Oliver T. Unke, Klaus-Robert Müller, Huziel E. Sauceda Published: 2026-03-23 Categories: cond-mat.mtrl-sci, cond-mat.mes-hall, cs.LG, physics.atm-clus, physics.chem-ph arXiv: https://arxiv.org/abs/2603.22254v1 Sodium-ion batteries require anodes that combine high capacity, low operating voltage, fast Na-ion transport, and mechanical stability, which conventional anodes struggle to deliver. Here, we use the SpookyNet machine-learning force field (MLFF) together with all-electron density-functional theory calculations to characterize Na storage in aminobenzene-functionalized Janus graphene (Na$_x$AB) at room-temperature. Simulations across state of charge reveal a three-stage storage mechanism-site-specific adsorption at aminobenzene groups and Na$_n$@AB$_m$ structure formation, followed by interlayer gallery filling-contrasting the multi-stage pore-, graphite-interlayer-, and defect-controlled behavior in hard carbon. This leads to an OCV profile with an extended low-voltage plateau of 0.15 V vs. Na/Na$^{+}$, an estimated gravimetric capacity of $\sim$400 mAh g$^{-1}$, negligible volume change, and Na diffusivities of $\sim10^{-6}$ cm$^{2}$ s$^{-1}$, two to three orders of magnitude higher than in hard carbon. Our results establish Janus aminobenzene-graphene as a promising, structurally defined high-capacity Na-ion anode and illustrate the power of MLFF-based simulations for characterizing electrode materials. --- ### EgoGroups: A Benchmark For Detecting Social Groups of People in the Wild Authors: Jeffri Murrugarra-Llerena, Pranav Chitale, Zicheng Liu, Kai Ao, Yujin Ham, Guha Balakrishnan, Paola Cascante-Bonilla Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22249v1 Social group detection, or the identification of humans involved in reciprocal interpersonal interactions (e.g., family members, friends, and customers and merchants), is a crucial component of social intelligence needed for agents transacting in the world. The few existing benchmarks for social group detection are limited by low scene diversity and reliance on third-person camera sources (e.g., surveillance footage). Consequently, these benchmarks generally lack real-world evaluation on how groups form and evolve in diverse cultural contexts and unconstrained settings. To address this gap, we introduce EgoGroups, a first-person view dataset that captures social dynamics in cities around the world. EgoGroups spans 65 countries covering low, medium, and high-crowd settings under four weather/time-of-day conditions. We include dense human annotations for person and social groups, along with rich geographic and scene metadata. Using this dataset, we performed an extensive evaluation of state-of-the-art VLM/LLMs and supervised models on their group detection capabilities. We found several interesting findings, including VLMs and LLMs can outperform supervised baselines in a zero-shot setting, while crowd density and cultural regions clearly influence model performance. --- ### Confidence-Based Decoding is Provably Efficient for Diffusion Language Models Authors: Changxiao Cai, Gen Li Published: 2026-03-23 Categories: cs.LG, cs.AI, cs.IT, stat.ML arXiv: https://arxiv.org/abs/2603.22248v1 Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models for language modeling, allowing flexible generation order and parallel generation of multiple tokens. However, this flexibility introduces a challenge absent in AR models: the \emph{decoding strategy} -- which determines the order and number of tokens generated at each iteration -- critically affects sampling efficiency. Among decoding strategies explored in practice, confidence-based methods, which adaptively select which and how many tokens to unmask based on prediction confidence, have shown strong empirical performance. Despite this success, our theoretical understanding of confidence-based decoding remains limited. In this work, we develop the first theoretical analysis framework for confidence-based decoding in DLMs. We focus on an entropy sum-based strategy that continues unmasking tokens within each iteration until the cumulative entropy exceeds a threshold, and show that it achieves $\varepsilon$-accurate sampling in KL divergence with an expected number of iterations $\widetilde O(H(X_0)/\varepsilon)$, where $H(X_0)$ denotes the entropy of the target data distribution. Notably, this strategy yields substantial sampling acceleration when the data distribution has low entropy relative to the sequence length, while automatically adapting to the intrinsic complexity of data without requiring prior knowledge or hyperparameter tuning. Overall, our results provide a theoretical foundation for confidence-based decoding and may inform the design of more efficient decoding strategies for DLMs. --- ### MemDLM: Memory-Enhanced DLM Training Authors: Zehua Pei, Hui-Ling Zhen, Weizhe Lin, Sinno Jialin Pan, Yunhe Wang, Mingxuan Yuan, Bei Yu Published: 2026-03-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.22241v2 Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, standard DLM training uses a static, single-step masked prediction objective that never exposes the model to the progressive denoising dynamics of inference, and forces all contextual information to be maintained purely through token-space attention, which becomes increasingly diluted as context length grows. We propose MemDLM (Memory-Enhanced DLM), which introduces a second memory channel by embedding a simulated denoising trajectory into training via Bi-level Optimization. An inner loop updates a set of fast weights, forming a Parametric Memory that captures the local trajectory experience, while an outer loop updates the base model conditioned on this memory. By offloading part of the memorization burden from token-space attention to parameter space, MemDLM yields faster convergence, stronger long-context representations, and lower training loss, even when the fast weights are discarded at inference time. Re-enabling the inner loop at inference provides an additional prompt-specific adaptation effect, where the Parametric Memory acts as an emergent in-weight retrieval mechanism on challenging Needle-in-a-Haystack tasks. Code: https://github.com/JarvisPei/MemDLM. --- ### ShapDBM: Exploring Decision Boundary Maps in Shapley Space Authors: Luke Watkin, Daniel Archambault, Alex Telea Published: 2026-03-23 Categories: cs.HC, cs.LG arXiv: https://arxiv.org/abs/2603.22235v3 Decision Boundary Maps (DBMs) are an effective tool for visualising machine learning classification boundaries. Yet, DBM quality strongly depends on the dimensionality reduction (DR) technique and high dimensional space used for the data points. For complex ML data, DR can create many mixed classes which yield DBMs that are hard to use or even misleading. We propose a new technique to compute DBMs by transforming data space into Shapley space and computing DR on it. Compared to DBMs computed directly from data, our maps have similar or higher quality metric values and visibly more compact, easier to explore, decision zones that better agree with measured model performance. --- ### One Model, Two Markets: Bid-Aware Generative Recommendation Authors: Yanchen Jiang, Zhe Feng, Christopher P. Mah, Aranyak Mehta, Di Wang Published: 2026-03-23 Categories: cs.IR, cs.AI, cs.GT, cs.LG arXiv: https://arxiv.org/abs/2603.22231v1 Generative Recommender Systems using semantic ids, such as TIGER (Rajput et al., 2023), have emerged as a widely adopted competitive paradigm in sequential recommendation. However, existing architectures are designed solely for semantic retrieval and do not address concerns such as monetization via ad revenue and incorporation of bids for commercial retrieval. We propose GEM-Rec, a unified framework that integrates commercial relevance and monetization objectives directly into the generative sequence. We introduce control tokens to decouple the decision of whether to show an ad from which item to show. This allows the model to learn valid placement patterns directly from interaction logs, which inherently reflect past successful ad placements. Complementing this, we devise a Bid-Aware Decoding mechanism that handles real-time pricing, injecting bids directly into the inference process to steer the generation toward high-value items. We prove that this approach guarantees allocation monotonicity, ensuring that higher bids weakly increase an ad's likelihood of being shown without requiring model retraining. Experiments demonstrate that GEM-Rec allows platforms to dynamically optimize for semantic relevance and platform revenue. --- ### Riverine Land Cover Mapping through Semantic Segmentation of Multispectral Point Clouds Authors: Sopitta Thurachen, Josef Taher, Matti Lehtomäki, Leena Matikainen, Linnea Blåfield, Mikel Calle Navarro, Antero Kukko, Tomi Westerlund, Harri Kaartinen Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22230v1 Accurate land cover mapping in riverine environments is essential for effective river management, ecological understanding, and geomorphic change monitoring. This study explores the use of Point Transformer v2 (PTv2), an advanced deep neural network architecture designed for point cloud data, for land cover mapping through semantic segmentation of multispectral LiDAR data in real-world riverine environments. We utilize the geometric and spectral information from the 3-channel LiDAR point cloud to map land cover classes, including sand, gravel, low vegetation, high vegetation, forest floor, and water. The PTv2 model was trained and evaluated on point cloud data from the Oulanka river in northern Finland using both geometry and spectral features. To improve the model's generalization in new riverine environments, we additionally investigate multi-dataset training that adds sparsely annotated data from an additional river dataset. Results demonstrated that using the full-feature configuration resulted in performance with a mean Intersection over Union (mIoU) of 0.950, significantly outperforming the geometry baseline. Other ablation studies revealed that intensity and reflectance features were the key for accurate land cover mapping. The multi-dataset training experiment showed improved generalization performance, suggesting potential for developing more robust models despite limited high-quality annotated data. Our work demonstrates the potential of applying transformer-based architectures to multispectral point clouds in riverine environments. The approach offers new capabilities for monitoring sediment transport and other river management applications. --- ### Benchmarking Deep Learning Models for Aerial LiDAR Point Cloud Semantic Segmentation under Real Acquisition Conditions: A Case Study in Navarre Authors: Alex Salvatierra, José Antonio Sanz, Christian Gutiérrez, Mikel Galar Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.22229v1 Recent advances in deep learning have significantly improved 3D semantic segmentation, but most models focus on indoor or terrestrial datasets. Their behavior under real aerial acquisition conditions remains insufficiently explored, and although a few studies have addressed similar scenarios, they differ in dataset design, acquisition conditions, and model selection. To address this gap, we conduct an experimental benchmark evaluating several state-of-the-art architectures on a large-scale aerial LiDAR dataset acquired under operational flight conditions in Navarre, Spain, covering heterogeneous urban, rural, and industrial landscapes. This study compares four representative deep learning models, including KPConv, RandLA-Net, Superpoint Transformer, and Point Transformer V3, across five semantic classes commonly found in airborne surveys, such as ground, vegetation, buildings, and vehicles, highlighting the inherent challenges of class imbalance and geometric variability in aerial data. Results show that all tested models achieve high overall accuracy exceeding 93%, with KPConv attaining the highest mean IoU (78.51%) through consistent performance across classes, particularly on challenging and underrepresented categories. Point Transformer V3 demonstrates superior performance on the underrepresented vehicle class (75.11% IoU), while Superpoint Transformer and RandLA-Net trade off segmentation robustness for computational efficiency. --- ### SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation Authors: Sashuai Zhou, Qiang Zhou, Junpeng Ma, Yue Cao, Ruofan Hu, Ziang Zhang, Xiaoda Yang, Zhibin Wang, Jun Song, Cheng Yu, Bo Zheng, Zhou Zhao Published: 2026-03-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.22228v1 Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most existing reward models pay limited attention to fine-grained spatial relationships, often producing images that appear plausible overall yet contain inaccuracies in object positioning. In this work, we present \textbf{SpatialReward}, a verifiable reward model explicitly designed to evaluate spatial layouts in generated images. SpatialReward adopts a multi-stage pipeline: a \emph{Prompt Decomposer} extracts entities, attributes, and spatial metadata from free-form prompts; expert detectors provide accurate visual grounding of object positions and attributes; and a vision-language model applies chain-of-thought reasoning over grounded observations to assess complex spatial relations that are challenging for rule-based methods. To more comprehensively evaluate spatial relationships in generated images, we introduce \textbf{SpatRelBench}, a benchmark covering object attributes, orientation, inter-object relations, and rendered text placement. Experiments on Stable Diffusion and FLUX show that incorporating SpatialReward into RL training consistently improves spatial consistency and overall generation quality, with results aligned more closely to human judgments. These findings indicate that verifiable reward models hold considerable potential for enabling more accurate and controllable optimization in text-to-image generation models. --- ### Dyadic: A Scalable Platform for Human-Human and Human-AI Conversation Research Authors: David M. Markowitz Published: 2026-03-23 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.22227v1 Conversation is ubiquitous in social life, but the empirical study of this interactive process has been thwarted by tools that are insufficiently modular and unadaptive to researcher needs. To relieve many constraints in conversation research, the current tutorial presents an overview and introduction to a new tool, Dyadic (https://www.chatdyadic.com/), a web-based platform for studying human-human and human-AI conversations using text-based or voice-based chats. Dyadic is distinct from other platforms by offering studies with multiple modalities, AI suggestions (e.g., in human-human studies, AI can suggest responses to a participant), live monitoring (e.g., researchers can evaluate, in real time, chats between communicators), and survey deployment (e.g., Likert-type scales, feeling thermometers, and open-ended text boxes can be sent to humans for in situ evaluations of the interaction), among other consequential features. No coding is required to operate Dyadic directly, and integrations with existing survey platforms are offered. --- ### Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease Authors: Abner Hernandez, Eunjung Yeo, Kwanghee Choi, Chin-Jou Li, Zhengjun Yue, Rohan Kumar Das, Jan Rusz, Mathew Magimai Doss, Juan Rafael Orozco-Arroyave, Tomás Arias-Vergara, Andreas Maier, Elmar Nöth et al. Published: 2026-03-23 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2603.22225v3 The limited availability of dysarthric speech data makes cross-lingual detection an important but challenging problem. A key difficulty is that speech representations often encode language-dependent structure that can confound dysarthria detection. We propose a representation-level language shift (LS) that aligns source-language self-supervised speech representations with the target-language distribution using centroid-based vector adaptation estimated from healthy-control speech. We evaluate the approach on oral DDK recordings from Parkinson's disease speech datasets in Czech, German, and Spanish under both cross-lingual and multilingual settings. LS substantially improves sensitivity and F1 in cross-lingual settings, while yielding smaller but consistent gains in multilingual settings. Representation analysis further shows that LS reduces language identity in the embedding space, supporting the interpretation that LS removes language-dependent structure. ---